Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Appeals
    -0.27
    ä¸Ģ举
    -0.27
    wers
    -0.26
     impl
    -0.26
    vais
    -0.26
    vil
    -0.26
    çľģåĨħ
    -0.26
    æĹłæķĮ
    -0.26
    æĹłåĬĽ
    -0.25
    rev
    -0.25
    POSITIVE LOGITS
    imeo
    0.27
    æĦıè§ģåıįé¦Ī
    0.26
    ä¸įçķĻ
    0.26
    quot
    0.26
    ifr
    0.26
    å®Įæķ´çļĦ
    0.26
    齿
    0.24
    itat
    0.24
    (Expected
    0.24
     exerc
    0.23
    Act Density 0.002%

    No Known Activations